Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    comparative phrases that denote a higher degree or quantity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Gass
    -0.78
    bufio
    -0.75
     Jäger
    -0.64
     koper
    -0.64
    ②
    -0.63
    xr
    -0.62
     Milano
    -0.59
    isser
    -0.58
     Monza
    -0.58
    Przypisy
    -0.57
    POSITIVE LOGITS
     THAN
    1.21
     Than
    1.01
     than
    1.00
    Than
    1.00
    THAN
    0.95
     dozen
    0.91
    iastes
    0.86
    CloseOperation
    0.82
    GreaterThan
    0.81
    OrEqual
    0.80
    Act Density 0.066%

    No Known Activations